drm/amdgpu: move preamble IB handling into common code

This fixes the handling which was completely broken when you
ad more than one preamble IB.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c

@@ -125,6 +125,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 	struct fence *hwf;
 	struct amdgpu_vm *vm = NULL;
 	unsigned i, patch_offset = ~0;
+	bool skip_preamble;
 
 	int r = 0;
 
@@ -172,9 +173,14 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 	/* always set cond_exec_polling to CONTINUE */
 	*ring->cond_exe_cpu_addr = 1;
 
+	skip_preamble = ring->current_ctx == ctx;
 	old_ctx = ring->current_ctx;
 	for (i = 0; i < num_ibs; ++i) {
-		ib = &ibs[i];
+
+		/* drop preamble IBs if we don't have a context switch */
+		if ((ib->flags & AMDGPU_IB_FLAG_PREAMBLE) && skip_preamble)
+			continue;
+
 		amdgpu_ring_emit_ib(ring, ib);
 		ring->current_ctx = ctx;
 	}

drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c

@@ -2036,10 +2036,6 @@ static void gfx_v7_0_ring_emit_ib_gfx(struct amdgpu_ring *ring,
 	u32 header, control = 0;
 	u32 next_rptr = ring->wptr + 5;
 
-	/* drop the CE preamble IB for the same context */
-	if ((ib->flags & AMDGPU_IB_FLAG_PREAMBLE) && !need_ctx_switch)
-		return;
-
 	if (need_ctx_switch)
 		next_rptr += 2;
 

drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c

@@ -5652,10 +5652,6 @@ static void gfx_v8_0_ring_emit_ib_gfx(struct amdgpu_ring *ring,
 	u32 header, control = 0;
 	u32 next_rptr = ring->wptr + 5;
 
-	/* drop the CE preamble IB for the same context */
-	if ((ib->flags & AMDGPU_IB_FLAG_PREAMBLE) && !need_ctx_switch)
-		return;
-
 	if (need_ctx_switch)
 		next_rptr += 2;